About

Professor Nicholas E. Jackson is an Assistant Professor of Chemistry at the University of Illinois Urbana-Champaign (UIUC) and leads the AI for Materials Group at the Beckman Institute for Advanced Science and Technology. He earned his B.A. in Physics from Wesleyan University and completed his Ph.D. in Chemistry at Northwestern University, where he worked with Professors Mark Ratner and Lin Chen. Following his doctoral studies, he was a Named Fellow and Assistant Scientist in the Materials Science Division at Argonne National Laboratory, collaborating with Professor Juan de Pablo. Professor Jackson's research focuses on the intersection of artificial intelligence, molecular modeling, and soft materials chemistry. His group's innovative work in these areas has been recognized by prestigious organizations including the Kavli Foundation, the Department of Energy, the Cottrell Scholar Program, the Dreyfus Foundation, AIChE COMSEF, ACS OpenEye, ACS Petroleum Research Fund, and 3M.

Research topics

• Materials science
• Artificial Intelligence
• Chemistry
• Computer Science
• Machine Learning
• Nanotechnology
• Chemical engineering
• Composite material
• Optics
• Polymer science
• Optoelectronics
• Chemical physics

Selected publications

• A Theory of Electronic Structure for Coarse-Grained Resolutions

  ChemRxiv · 2026-02-18

  articleOpen access1st authorCorresponding

  We present a stochastic diabatic projection method for constructing electronic structure models that operate at coarse-grained (CG) molecular resolutions. By minimizing the relative entropy of joint electronic-nuclear distributions between the fine-grained and CG resolutions, we derive a stochastic effective Hamiltonian that decomposes CG configuration dependent interactions into deterministic means and residual fluctuations. This framework bridges downfolding theory with data-driven CG modeling, enabling the accurate reproduction of electronic properties renormalized over eliminated nuclear and electronic degrees of freedom.

  PublisherDOI

• On the Prospect of Chemically Transferable Coarse-Grained Electronic Models for Soft Materials

  ChemRxiv · 2026-02-08

  articleOpen accessSenior author
  PublisherDOI

• Machine-learning graph convolutional electronic propagators

  The Journal of Chemical Physics · 2026-01-22

  articleSenior author

  We present a graph-based machine-learning framework for simulating the time evolution of electronic wavefunctions and densities in quantum systems. Inspired by parallels between time-dependent quantum propagators and spectral graph convolutions, we employ a recursive Chebyshev graph neural network architecture capable of learning the dynamics of electronic processes across a range of external potentials and Hamiltonians. Two model variants are introduced: one that evolves the full complex-valued wavefunction and the other that propagates only the electron density. Both models are trained on trajectory data generated from tight-binding Hamiltonians and a time-dependent electron-phonon coupled system. Our results demonstrate that wavefunction-based models achieve near-exact long-time propagation across static and dynamic regimes, while density-only models maintain strong performance using physics-informed loss functions, even in the absence of phase information. This work lays the foundation for coarse-grained, resolution-independent propagators for electronic dynamics and opens new pathways for scalable quantum simulations in complex molecular and condensed-phase systems.

  PublisherDOI

• On the Prospect of Chemically Transferable Coarse-Grained Electronic Models for Soft Materials

  The Journal of Physical Chemistry B · 2026-05-12

  articleSenior author

  Electronic coarse-graining (ECG) methods predict quantum-mechanical electronic properties directly from coarse-grained (CG) molecular configurations, enabling electronic predictions at mesoscopic length scales. Here, we present a diagnostic assessment of the feasibility of chemically transferable ECG models at predicting the HOMO energy across a broad polymer-relevant chemical space using all-atom, united-atom, and Martini-scale representations. A fundamental challenge at the Martini resolution is the many-to-one mapping degeneracy, in which chemically distinct moieties map to identical bead sequences, precluding a one-to-one correspondence between bead coordinates and electronic properties. We demonstrate that our proposed Element-Count-Label (ECL) representation, which augments Martini beads with explicit stoichiometric data and reduces this representation degeneracy, significantly improves chemical generalization across diverse polymer chemistries. However, we show that the CG force field does not sample the same configurational distribution of local molecular structure as that underlying the DFT-parametrized ECG model, and that even with improved chemical resolution, the model cannot recover electronic property distributions that are absent from the configurational space sampled by the CG force field. These results demonstrate that chemically transferable ECG requires future Martini-like force fields to explicitly preserve quantum chemistry-compatible local molecular structure in addition to macroscopic thermodynamic and structural fidelity.

  PublisherDOI

• Frontier-Orbital Predictions from Coarse-Grained Geometries with Physics-Constrained Neural Hamiltonians

  ChemRxiv · 2026-02-02

  articleOpen accessSenior author

  We introduce a physics-informed machine learning framework, Orbital Electronic Coarse-Graining (Orb-ECG), for predicting frontier molecular orbital energies at coarse-grained (CG) molecular resolutions. Orb-ECG constructs a realspace overlap matrix by projecting a Gaussian orbital basis onto the CG representation and employs a neural-networkparameterized expansion of this overlap matrix to reproduce quantum-chemistry-derived eigenvalues. This model is trained end-to-end using a composite loss enforcing energy accuracy, basis localization, sparsity, and smoothness. When evaluated on bithiophene conformations, Orb-ECG demonstrates improved data efficiency and extrapolation performance relative to a physics-agnostic ML benchmark while remaining competitive in the large-data limit. In addition to orbital energies, Orb-ECG provides a CG orbital basis that enables access to 3D CG pseudo-orbitals. These CG pseudo-orbitals reliably capture average population trends, but are limited in their ability to capture conformationinduced fluctuations in the electron density, motivating future work. These method developments establish a physically grounded avenue toward efficient and generalizable electronic structure modeling at CG molecular resolutions.

  PublisherOA PDFDOI

• Computational Exploration of the Structure and Mechanical Behaviour of Hybrid Epoxy-Acrylate Dual-Cure Systems †

  ChemRxiv · 2026-02-10

  articleOpen accessSenior author

  Wavelength-selective dual-cure epoxy-acrylate polymers have recently been demonstrated experimentally as a platform for generating large mechanical contrasts from a single material system for additive manufacturing [Kim et al., Nature Materials, 2025, 24, 1116-1125], motivating the need for a molecular-level understanding of how network structure and crosslinking governs the mechanical response in such hybrid systems. Here, we use coarse-grained molecular dynamics simulations to investigate the structural, thermal, and mechanical evolution of a model hybrid epoxy-acrylate network spanning elastomeric and thermoset regimes. By systematically varying network architecture, chain length, bond stiffness, and epoxy conversion, we show that elastomer stiffness is highly sensitive to the topology of the initial acrylate network, whereas thermoset stiffness becomes largely insensitive to these structural details once dense epoxy connectivity is established. Tracking network evolution across epoxy conversion reveals a transition that emerges beyond approximately 40% epoxy crosslinking, after the formation of a system-spanning elastomeric network, where network topology becomes increasingly heterogeneous and deformation mechanisms shift from predominantly entropic elasticity to energy-dominated load transfer involving localized covalent bond stretching. This crossover marks the onset of thermoset-like load transfer, with subsequent crosslinking further strengthening this response as stiffness and bond-level deformation increase smoothly. Together, these results provide a framework for understanding how mechanical contrast in wavelength-selective dual-cure polymer networks emerges from the interplay between elastomeric network topology and a connectivity-driven crossover in deformation mechanisms induced by epoxy crosslinking.

  PublisherOA PDFDOI

• Accessing Solid-State 13C NMR Prediction in Polymers with Machine-Learned Chemical Shifts

  ChemRxiv · 2026-04-06

  articleOpen accessSenior author

  Solid-state 13C nuclear magnetic resonance (NMR) spectroscopy is among the most powerful probes of polymer structure, yet predicting solid-state 13C NMR spectra from molecular simulations has remained infeasible due to intractable computational costs. Here we introduce PNGWNN, a framework coupling molecular dynamics and machinelearned chemical shifts to efficiently generate solid-state 13C NMR spectra from molecular simulation. Trained on three polymer chemistries, PNGWNN achieves ∼1 ppm chemical shift prediction accuracy against density functional theory and transfers quantitatively to six chemically distinct test polymers across amorphous, crystalline, surface, multiphase, and copolymer morphologies. Moreover, predicted spectral features can be decomposed into atomically detailed contributions associated with specific conformations, hydrogen-bond motifs, and phase compositions, revealing structure–spectrum relationships without prior structural hypotheses. PNGWNN makes solid-state 13C NMR a computationally accessible observable, opening routes to simulation-driven structural inference and experimental design in polymers.

  PublisherDOI

• Generative Multi-Property Refinement of Polymer Chemistries

  ChemRxiv · 2026-02-22

  articleOpen accessSenior author

  We present a generative, multi-objective optimization method for polymer chemistry. By leveraging monomer-level properties that are directly correlated with polymer properties, we design targeted step-growth polymers with desired glass transition temperatures (T g), band gaps (E g), and Flory-Huggins interaction parameters with water (χ water) across a broad chemical space. Generative design is accomplished using a variational autoencoder integrated with linear property prediction heads. Linear organization of the latent space enables the identification of a single latent vector to steer 1 the simultaneous optimization of multiple polymer property objectives. Subsequent Bayesian optimization within the latent space allows further enhancement of T g , E g , and χ water relative to a reference polymer chemistry. We subsequently applied the generative model to design per-and polyfluoroalkyl substances (PFAS)-based polymers with reduced fluorine content but comparable physical properties. Overall, this work establishes a generative, multi-objective approach for navigating early-stage polymer design, prior to experimental validation or computationally expensive simulations.

  PublisherOA PDFDOI

• Computational Insights into the Salt-Induced Modulation of Electron Transporting Conjugated Polyelectrolytes

  Macromolecules · 2026-03-05

  articleSenior authorCorresponding

  The morphological and electronic properties of conjugated polyelectrolytes (CPEs) are highly sensitive to their ionic environment and remain poorly understood. To elucidate structure–property relationships in CPEs, we investigate the role of salt concentration on CPE morphology and hole conductivity using a quantum mechanically informed coarse-grained (CG) model coupled with semiclassical rate theory. Under good solvent conditions, high salt concentration induces torsional disorder along the conjugated backbone, decreasing hole delocalization. In contrast, under poor solvent conditions, high salt concentration promotes CPE aggregation, leading to thicker fibers and increased hole mobilities. Collectively, this work characterizes the competing interactions governing CPE assembly and hole transport as a function of salt concentration, highlighting ion engineering as a powerful strategy for tailoring the properties of mixed-conducting polymers.

  PublisherDOI

• Molecular Charge Topologies Govern Polar Nematic Ordering

  ChemRxiv · 2025-10-27

  articleSenior author

  Polar nematic phases exhibit spontaneous macroscopic polarization while retaining the orientational order of conventional nematics, offering opportunities for responsive optical and electronic materials. The molecular determinants of polar order remain elusive, as traditional design strategies focus on the magnitude of the dipole moment without reliable prediction. We analyze charge topologies of a curated dataset of 236 nematic compounds by computing their sigma-profiles and charge-weighted Graph Fourier Transforms (GFT). We show that machine learning classification using a single order parameter derived from GFT can accurately distinguish polar and apolar nematic formers and outperforms dipolar and sigma-profile metrics. This framework provides a physically interpretable and computationally lightweight approach capable of identifying topological motifs governing spontaneous polarization.

  PublisherDOI

Recent grants

• Electronic Structure Models Using Coarse-Grained Representations

  NSF · $450k · 2022–2026

Frequent coauthors

• Juan Pablo

  Argonne National Laboratory

  100 shared

• Lin X. Chen

  Northwestern University

  55 shared

• Matthew Tirrell

  Argonne National Laboratory

  27 shared

• Mark A. Ratner

  Theralogix (United States)

  26 shared

• Brett M. Savoie

  16 shared

• Boyuan Yu

  15 shared

• Megan L. Shelby

  Lawrence Livermore National Laboratory

  15 shared

• Charles M. Schroeder

  Nathan Kline Institute for Psychiatric Research

  15 shared

Labs

• The Jackson LabPI

  AI for Materials Group at the Beckman Institute for Advanced Science and Technology

Education

• Ph.D., Chemistry

  Northwestern University

  2016

• B.A. w/High Honors, Physics

  Wesleyan University

  2011

Awards & honors

• Camille Dreyfus Teacher-Scholar Award (2025)
• Cottrell Scholar Award (2025)
• Kavli Foundation Emerging Leader in Chemistry Award (2024)
• AIChE COMSEF Young Investigator Award (2024)
• Center for Advanced Study Fellow, UIUC (2024)